Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to individuals or people in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    who followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.41
    ,
    -0.41
    isEdit
    -0.39
     Sanford
    -0.38
    false
    -0.38
     Seitz
    -0.37
    logitech
    -0.36
     Gass
    -0.35
     './../
    -0.34
    urnia
    -0.33
    POSITIVE LOGITS
     who
    1.21
     którzy
    1.09
     kteří
    0.97
    who
    0.94
    Who
    0.92
     Who
    0.91
     whom
    0.91
     ktorí
    0.87
     który
    0.83
     الذين
    0.81
    Act Density 0.049%

    No Known Activations